{"ok":true,"nota":{"id":"ae82a60be0466807","slug":"una-inteligencia-artificial-detecta-el-tipo-de-cancer-de-vulva-mirando-ae82a6","titulo":"Una inteligencia artificial detecta el tipo de cáncer de vulva mirando solo una lámina de tejido teñida","resumen":"Investigadores entrenaron modelos de aprendizaje profundo con imágenes digitales de biopsias de cáncer de vulva. Lograron identificar si el tumor estaba asociado al virus HPV y su subtipo molecular, sin necesidad de análisis químicos adicionales.","fuente":"medrxiv","fuenteNombre":"medRxiv · preprints","color":"#1f7a4d","autor":"van den Berg, N., van der Kolk, W., Landsbergen, K., Kortekaas, K., Nooij, L., van Velzen, A. F., te Grootenhuis, N., th","url":"https://www.medrxiv.org/content/10.64898/2026.10.22.26366203v1?rss=1","imagen":"/hoy/portada/ae82a60be0466807","tema":"ciencia","subtemas":["inteligencia artificial","cáncer de vulva","patología digital","virus hpv","diagnóstico médico"],"entidades":["medRxiv"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-24T00:00:00.000Z","indexTs":"2026-10-24T17:16:27.916Z","hash":"209a728c5c9690de1f0205d90edfacc2c89d500a22d5e9aa025de4335fd5a00a","tsa":{"time":"Oct 24 17:16:46 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Hoy clasificar este cáncer exige pruebas extra que consumen tejido y no siempre están disponibles, sobre todo en estudios de historias clínicas antiguas. Una herramienta que lo resuelva con la lámina de rutina podría ahorrar tiempo y muestras en hospitales con menos recursos, incluidos muchos de Argentina. Igual, todavía hace falta validarla con más pacientes antes de usarla en la práctica diaria.","quienFirma":"Estudio publicado en medRxiv (institución principal no identificada en el resumen)","confianza":"preprint","consulta":null},"sello":{"hash":"209a728c5c9690de1f0205d90edfacc2c89d500a22d5e9aa025de4335fd5a00a","sello":"a570737b5428d9d180027ea5d3e0ab8b519c9c281869f0ef5adac549fe8be2b1","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6581039,"aleatorio":"d99a692560dbc2ba47d0f7eede43fd898f749a62d19940a97e01ee43a1111cab","tiempo":"2026-10-24T17:16:30.000Z"},"nist":{"cadena":2,"pulso":1997713,"salida":"8365CC9CEC8EE66D4760C1579F407D2310605DD2803C2223B88DBDCEB795D273C1B45B3DCF4ED9665A430963C6E366E8D294D3F7E695989F155365311750A2FB","tiempo":"2026-10-24T17:16:00.000Z"},"noAntes":"2026-10-24T17:16:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 24 17:16:46 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Predicting HPV/p16 Status and Molecular Subtypes from Histopathology Slides using Deep Learning in Vulvar Squamous Cell Carcinoma","descripcion":"Vulvar squamous cell carcinoma (VSCC) comprises three prognostically distinct molecular subtypes: human papillomavirus (HPV)-associated, HPV-independent/p53-wildtype, and HPV-independent/p53-abnormal. Classification requires p16/p53 immunohistochemistry, which consumes tissue and is often incomplete in retrospective cohorts. We investigated whether deep learning could predict HPV/p16 status and molecular subtypes directly from routine hematoxylin and eosin-stained whole-slide images. Using features extracted with H-optimus-1, we developed two attention-based multiple-instance learning models: HERA, predicting HPV/p16 status, and HERMES, predicting the three molecular subtypes. Models were de","pubDate":"2026-10-24","url":"https://www.medrxiv.org/content/10.64898/2026.10.22.26366203v1?rss=1"},"indexado":"2026-10-24T17:16:27.916Z"}}